TEST #32 RESULTS
03/28/2025 - 5:25 PM
ACCELERATOR
MODEL
76.6
tokens/s
generation
1.18
sec
time to first token
1110
tokens/s
prompt
416
LocalScore
HOW YOU STACK UP
Explore All ResultsLlama 3.2 1B Instruct - Q4_K - Medium
SYSTEM
CPU
Apple M4 4P+6E
RAM
16GB
OS
Darwin
Kernel Release
24.1.0
Architecture
arm64
Version
Cosmopolitan 3.9.7 MODE=aarch64; Darwin Kernel Version 24.1.0: Thu Oct 10 21:06:23 PDT 2024; root:xnu-11215.41.3~3/RELEASE_ARM64_T8132
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
1328
tokens/s
84.8
tokens/s
783
ms
pp4096+tg256
977
tokens/s
55.3
tokens/s
4.21
sec
pp2048+tg256
1200
tokens/s
71.1
tokens/s
1.72
sec
pp2048+tg768
1202
tokens/s
68.7
tokens/s
1.72
sec
pp1024+tg1024
1317
tokens/s
78.3
tokens/s
789
ms
pp1280+tg3072
1294
tokens/s
65.2
tokens/s
1.00
sec
pp384+tg1152
1334
tokens/s
85.9
tokens/s
299
ms
pp64+tg1024
980
tokens/s
91.8
tokens/s
76
ms
pp16+tg1536
356
tokens/s
88.4
tokens/s
55
ms